The four heights
The same task, four distances: today's deadline, the next reviewer, the stuck moment, the pattern.
Execute — do the immediate task
+The quarterly results workbook and appendices are ready; send the compiled report to Dr. Lee in…
Execute — do the immediate task
+The quarterly results workbook and appendices are ready; send the compiled report to Dr. Lee in Epidemiology and to Sara in Publications for sign-off, signers in that order, with Wednesday at noon as the deadline — verify that the methodology appendix includes raw counts and smoothing parameters before sending.
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Improve — make it easier to accept
+Before this goes to publications, make the report reviewer-friendly: move the headline prevalence…
Improve — make it easier to accept
+Before this goes to publications, make the report reviewer-friendly: move the headline prevalence and confidence interval to the executive summary, make the trend chart downloadable as a PNG, call out any data exclusions and why they matter, and flag cells where imputation changed conclusions.
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Decide — diagnose the stuck moment
+I completed the report and distributed it to Dr. Lee and Sara, then learned the lab corrected a…
Decide — diagnose the stuck moment
+A dataset used for the report was updated after I ran the analysis
I completed the report and distributed it to Dr. Lee and Sara, then learned the lab corrected a sequencing batch and the prevalence numbers shifted slightly. I cannot tell Publications we used preliminary counts without undermining their timeline. Do I withdraw the report and delay release to reconcile, or append a correction note and proceed? Which keeps credibility highest with stakeholders and what wording will limit rework later?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Become — change the pattern
+We repeatedly publish reports that need corrections when upstream data revisions arrive late,…
Become — change the pattern
+Repeated last-minute data corrections force report reissues
We repeatedly publish reports that need corrections when upstream data revisions arrive late, wasting time on re-approval and confusing readers. Where should we change our gating or routines so the reports are stable at distribution and we avoid repeating corrections?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Where the evidence lives
Who was seen doing this, and what people really ask.
Cell BiologistComputational BiologistData Quality AnalystField BiologistMarine BiologistPharma Formulation Scientistalso: Compile reports on the daily activitiesalso: Prepare reports
Software tasks in the LLOS Work Atlas come from evidence, never a feature list: careers attested to do the work, real job descriptions, and the questions people actually ask (with their view counts). Facets — feature, workflow, troubleshoot, administer, deploy, scale — are open metadata: the work decides, not a taxonomy.
Copyright © LLOS.ai · 2026 — original pedagogy, voice, and design — all rights reserved.
The rest of the map
Same library, five ways in.